Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    script tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    antium
    0.39
     communal
    0.37
    зера
    0.37
    作
    0.36
    Laut
    0.35
     propaganda
    0.35
     resource
    0.34
     filters
    0.34
     narrative
    0.34
    inios
    0.34
    POSITIVE LOGITS
     സൂര്യ
    0.43
     parec
    0.42
    script
    0.42
    FlagSet
    0.39
     जीव
    0.39
    атр
    0.39
     সম্পন্ন
    0.38
     প্রতিযোগ
    0.38
    umont
    0.37
    instrList
    0.37
    Act Density 0.001%

    No Known Activations